Method of performing a user-specific and device-specific calibration of point of gaze estimation

1. A method of calibrating point of gaze estimation, comprising the steps:

providing a calibration application;

providing a user device;

wherein said user device comprises a display and a user-facing camera;

wherein said calibration application runs on said user device;

wherein said calibration application causes to be displayed on said display a series of calibration markers;

prompting a user to look at said series of calibration markers by displaying said series of calibration markers on said display;

capturing one or more images of said user as said user is prompted to look at said series of calibration markers;

wherein a series of coordinates on said display is recorded for each of said series of calibration markers;

wherein said series of coordinates comprise a series of target ground truth positions for said series of calibration markers, which comprise a target ground truth position data;

generating a calibration data set by matching said target ground truth position data with said captured images;

processing said calibration data set by a Point of Gaze (“PoG”) estimation pipeline to generate PoG output data; wherein said target ground truth position data and PoG output data comprise a processed calibration data set;

splitting, by a calibration data set splitter, said processed calibration data set into a training calibration data set and a validation calibration data set;

processing, by a support vector regression calculator, said training calibration data set by utilizing one or more SVR training algorithms;

wherein said one or more SVR training algorithms are used to generate one or more SVR models after processing said training calibration data set;

calculating a preliminary positional gaze data for each of said one or more SVR models by utilizing said validation calibration data set;

comparing said preliminary positional gaze data against said validation calibration data set to calculate a mean absolute error for each data point of said validation calibration data set; and

wherein a best SVR model is selected from said one or more SVR models based on which of said SVR model has a lowest mean absolute error.

2. The method of calibrating point of gaze estimation of claim 1 ,

wherein said user comprises one or more user characteristics;

wherein said one or more user characteristics comprise gender, skin color, eye shape, age, hair, background color, and lighting conditions; and

wherein said SVR models are derived from processing one or more images of a model person having similar user characteristics as said user.

3. The method of calibrating point of gaze estimation of claim 1 ,

wherein said validation calibration data set may be used to calculate preliminary positional gaze data for each of said one or more SVR models; wherein said preliminary positional gaze data can be compared against said validation calibration data set to calculate a mean absolute error for each data point of said validation calibration data set;

wherein a best SVR model is determined from said one or more SVR models based on an individual SVR model with a lowest mean absolute error.

4. The method of calibrating point of gaze estimation of claim 3 , wherein said best SVR model fine-tunes said preliminary positional gaze data.

5. The method of calibrating point of gaze estimation of claim 1 , wherein said series of calibration markers are sequentially displayed in random locations on said display.

6. The method of calibrating point of gaze estimation of claim 1 ,

wherein said training calibration data set and said validation calibration data set are split by said calibration data set splitter into a 70/30 ratio, respectively.

7. A method of calibrating point of gaze estimation, comprising the steps:

providing a calibration application;

providing a user device;

wherein said user device comprises a display and a user-facing camera;

wherein said calibration application is configured to run on said user device;

wherein said calibration application is configured to cause to be displayed on said display a series of calibration markers;

wherein said calibration application is configured to prompt a user to look at said series of calibration markers by displaying said series of calibration markers on said display;

wherein said calibration application is configured to capture one or more images of said user as said user is prompted to look at said series of calibration markers;

wherein a series of coordinates on said display is configured to be recorded for each of said series of calibration markers;

wherein said series of coordinates comprise a series of target ground truth positions for said series of calibration markers, which comprise a target ground truth position data;

wherein said calibration application is configured to generate a calibration data set by matching said target ground truth position data with said captured images; and

wherein said calibration application is configured to process said calibration data set by a Point of Gaze (“PoG”) estimation pipeline to generate PoG output data; wherein said target ground truth position data and PoG output data comprise a processed calibration data set;

splitting, by a calibration data set splitter, said processed calibration data set into a training calibration data set and a validation calibration data set;

processing, by a support vector regression calculator, said training calibration data set by utilizing one or more SVR training algorithms;

wherein said one or more SVR training algorithms are used to generate one or more SVR models after processing said training calibration data set;

calculating a preliminary positional gaze data for each of said one or more SVR models by utilizing said validation calibration data set;

comparing said preliminary positional gaze data against said validation calibration data set to calculate a mean absolute error for each data point of said validation calibration data set; and

wherein a best SVR model is selected from said one or more SVR models based on which of said SVR model has a lowest mean absolute error.

8. The method of calibrating point of gaze estimation of claim 7 , wherein said validation calibration data set may be used to calculate preliminary positional gaze data for each of said one or more SVR models; wherein said preliminary positional gaze data can be compared against said validation calibration data set to calculate a mean absolute error for each data point of said validation calibration data set;

wherein a best SVR model is determined from one or more SVR models based on an individual SVR model with a lowest mean absolute error.

9. The method of calibrating point of gaze estimation of claim 8 , wherein said best SVR model fine-tunes said preliminary positional gaze data.

10. The method of calibrating point of gaze estimation of claim 7 , wherein said series of calibration markers are sequentially displayed in random locations on said display.

11. The method of calibrating point of gaze estimation of claim 7 , wherein said training calibration data set and said validation calibration data set are split by said calibration data set splitter into a 70/30 ratio, respectively.

12. A method of calibrating point of gaze estimation, comprising the steps:

providing a calibration application;

providing a user device;

wherein said user device comprises a display and a user-facing camera;

wherein said calibration application runs on said user device;

wherein said calibration application causes to be displayed on said display a series of calibration markers;

prompting a user to look at said series of calibration markers by displaying said series of calibration markers on said display;

capturing one or more images of said user as said user is prompted to look at said series of calibration markers;

wherein a series of coordinates on said display is recorded for each of said series of calibration markers;

wherein said series of coordinates comprise a series of target ground truth positions for said series of calibration markers, which comprise a target ground truth position data;

generating a calibration data set by matching said target ground truth position data with said captured images;

processing said calibration data set by a Point of Gaze (“PoG”) estimation pipeline to generate PoG output data;

wherein said target ground truth position data and PoG output data comprise a processed calibration data set;

splitting, by a calibration data set splitter, said processed calibration data set into a training calibration data set and a validation calibration data set;

processing, by a support vector regression calculator, said training calibration data set by utilizing one or more SVR training algorithms;

wherein said one or more SVR training algorithms are used to generate one or more SVR models after processing said training calibration data set;

calculating a preliminary positional gaze data for each of said one or more SVR models by utilizing said validation calibration data set;

comparing said preliminary positional gaze data against said validation calibration data set to calculate a mean absolute error for each data point of said validation calibration data set;

wherein a best SVR model is selected from said one or more SVR models based on which of said SVR model has a lowest mean absolute error;

wherein said validation calibration data set may be used to calculate preliminary positional gaze data for each of said one or more SVR models; wherein said preliminary positional gaze data can be compared against said validation calibration data set to calculate a mean absolute error for each data point of said validation calibration data set;

wherein the best SVR model is determined from said one or more SVR models based on an individual SVR model with a lowest mean absolute error; and

wherein said SVR model with a lowest mean absolute error fine-tunes said preliminary positional gaze data.